Optimizing Cancer Detection: Swarm Algorithms Combined with Deep Learning in Colon and Lung Cancer using Biomedical Images

Cancer is a deadly disorder, which affected by a mixture of genetic illnesses and a diversity of organic anomalies. Colon and lung cancer has been arisen as dual of the foremost origins of disability and death in humans. The histopathological recognition of such diseases is generally the most significant module in defining the finest progress of action. Prompt disease recognition on both front significantly reduces the probability of death. Machine learning (ML) and deep learning (DL) approaches are employed to haste up cancer recognition, letting researchers to analysis a great amount of patients in a short period of time and at a low cost. This research presents an Optimizing Cancer Detection using whale optimizer with Deep Learning in Colon and Lung Cancer (OCDWO-DLCLC) model on Biomedical Images. The presented OCDWO-DLCLC technique makes use of biomedical images for the recognition of colon and lung cancer. To achieve this, the OCDWO-DLCLC system uses wiener filtering (WF) technique for noise elimination process. In addition, the OCDWO-DLCLC technique uses NASNet Mobile model for learning complex feature patterns. Also, the hybrid of convolutional bidirectional gated recurrent unit (CNN‐BiGRU) model was applied for classifying the existence of colon and lung cancer in the biomedical images. Eventually, the whale optimization algorithm (WOA) is used to optimally choose the hyperparameters of the CNN‐BiGRU model. To confirm the improved analytical outcomes of the OCDWO-DLCLC approach, extensive simulations are executed on benchmark dataset. The comparative outcome analysis displays the promising performance of the OCDWO-DLCLC method on the recent models.